© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 6560
    Prev
    Next
    INDEX
    Explanations

    angle brackets and the text between them

    oai_token-act-pair · gemini-2.0-flash

    foreign words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Houſe
    -0.81
     myſelf
    -0.78
     pleaſure
    -0.73
    opardy
    -0.73
     itſelf
    -0.72
     Majefty
    -0.71
     Diſ
    -0.69
     Reſ
    -0.69
     Chriftian
    -0.68
     ſeveral
    -0.66
    POSITIVE LOGITS
     متعلقه
    0.58
     ddelweddau
    0.48
     odkazy
    0.45
     onCancelled
    0.44
     por
    0.43
    Референце
    0.42
    ույ
    0.42
     arşivlendi
    0.42
    Viited
    0.41
    autogui
    0.41
    Activations Density 24.294%

    No Known Activations